Comments (4)
E.g. can get stuck/slow in:
elif isinstance(chat_message, str):
children = self.md.parseInline(chat_message)[0].children
if children and any("code" in child.tag for child in children):
return self.md.render(chat_message)
else:
chat_message = chat_message.replace("\n", "<br>")
return self.md.renderInline(chat_message)
else:
raise ValueError(f"Invalid message for Chatbot component: {chat_message}")
from h2ogpt.
This hack fixes it:
elif isinstance(chat_message, str):
children = self.md.parseInline(chat_message)[0].children
if children and any("code" in child.tag for child in children):
return chat_message # self.md.render(chat_message)
else:
chat_message = chat_message.replace("\n", "<br>")
return chat_message #self.md.renderInline(chat_message)
else:
raise ValueError(f"Invalid message for Chatbot component: {chat_message}")
But I don't see option to disable markdown processing gradio, and a bit odd that is so slow. They must have loops in loops or something.
from h2ogpt.
Still shows formatted output in gradio output despite no md processing:
from h2ogpt.
fixed with newer gradio
from h2ogpt.
Related Issues (20)
- Offline mode is still attempting to fetch from HF HOT 4
- Use auto ingest with openai Api HOT 1
- Error installing through full linux bash script HOT 2
- Getting "an unexpected keyword argument 'cache_folder'" during import HOT 1
- .clone() fix both parent and clone for session hash HOT 2
- Missing instructions for make_db in docker HOT 7
- system_prompt ignored for response_format JSON -- use text_context_list instead? HOT 6
- TypeError: 'ResponseFormat' object is not subscriptable HOT 1
- databricks
- Metrics for the generated answer HOT 1
- Running RAG optimized models (nvidia/Llama3-ChatQA-1.5-70B) HOT 2
- add ingestion for OpenAI API HOT 1
- for image batching, do parallel jobs instead of many images per batch, some models just not good enough to handle multiple images HOT 1
- integrate stuff like LARS for PDF citations highlighting
- action model integration
- report generation
- RAG via open-webui
- Parallelize image calls instead of multiple images, probably better results in some cases
- Support private CA HOT 8
- Running model on multiple GPUs? How to do it? Does h2ogpt allows it do easily? HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from h2ogpt.